检索结果-内蒙古大学图书馆

An Efficient Real-Time Vehicle Monitoring Method

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2022年第11期23卷 22073-22083页

作者： Ye, Zhoujing Wei, Ya Zhang, Weidong Wang, Linbing Univ Sci & Technol Beijing Natl Ctr Mat Serv Safety Beijing 100083 Peoples R China Tsinghua Univ Dept Civil Engn Beijing 100084 Peoples R China Virginia Tech Coll Engn Blacksburg VA 24061 USA

As the major transportation infrastructure, roads play an important role in intelligent transportation system. However, the intelligent level of roads is insufficient currently, which does not match the development needs of autonomous vehicles in the near future. In order to improve the intelligence level of road infrastructures, a distributed acceleration sensing node array was embedded in the pavement to collect pavement vibration signals under the action of vehicle moving load to sense the traffic information. A complete set of processing algorithms, including raw data preprocessing algorithm, same vehicle judgment algorithm and vehicle information analysis algorithm, is proposed to extract the traffic information from the monitored vibration data. The traffic information such as vehicle speed, axle numbers, wheelbases, load position, and traffic flows are obtained. The acquired traffic information can support intelligent traffic control as well as scientific road maintenance.

关键词： Sensors vibrations Monitoring Axles Sensor systems Roads optical sensors Vehicle monitoring pavement vibration distributed multi-nodes pretreatment artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Rapid identification of rumors based on BERT and CNN

Rapid identification of rumors based on BERT and CNN

引用

2024 International Conference on Computer Application and information Security, ICCAIS 2024

作者： Zhu, Huaizhong Ran, Lina Li, Wanlu Zhao, Yanni Wang, Lisha Ling, Xufeng Department of Computer Science Shanghai Normal University Tianhua College Shanghai201815 China Department of Information Shanghai Customs College Shanghai201204 China

ISBN: (纸本)9781510689312

Rumor detection is a process designed to identify and analyze false or misleading content in information. The rapid development of social media is an important channel for people to obtain external information, and also a platform for the widespread dissemination of false news. In view of this phenomenon, this paper analyzes the key elements such as time, place, people and events in the news text information by algorithm, and uses the algorithm to analyze the social media, multiple information such as news sources, historical data, and comprehensively analyze the authenticity of the news between the two. This paper mainly introduces the steps and methods of Bidirectional Encoder Representations from Transformers model and Bidirectional Encoder Representations from Transformers-Convolutional Neural Network model in capturing text information, and tests and optimizes the algorithm. The test results show that these two algorithms can efficiently and quickly identify most of the fake news, and intuitively show them to users through the system output, which is worth applying and popularizing in the corresponding field. © The Authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Research on intrusion detection method of party building network in colleges and universities based on machine learning

Research on intrusion detection method of party building net...

引用

2024 International Conference on Signal processing and Communication Security, ICSPCS 2024

作者： Fan, Chaozhi Beijing Information Science and Technology University Beijing100192 China

ISBN: (纸本)9781510681699

The rapid development of the Internet and the intelligent information age have provided more possibilities for data leakage, network attacks and other behaviors of malicious persons. The network security of party building in colleges and universities faces severe challenges. Intrusion detection is a new information security technology used to detect intrusions in computer network systems. Intrusion detection methods based on machine learning can better identify unknown anomalies than rule-based methods. The essence of the intrusion detection problem is a classification problem. There are many classification methods in machine learning, including convolutional neural networks, naive Bayes, SVM, etc. These algorithms have good classification performance on balanced data sets. How to extract more representative attribute features from complex data sets to more accurately describe normal behavior and intrusion behavior has become an important breakthrough point in current intrusion detection solutions based on machine learning. In order to solve the problem of network intrusion for party building in universities, this paper proposes to apply the convolutional neural network algorithm and random forest algorithm in machine learning to the intrusion detection model of party building network in universities, which effectively improves the overall classification accuracy of the model and the recognition rate of minority classes. © 2024 SPIE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

A Parametric State-Space Network for Global Impairments Compensation in optical systems 15

A Parametric State-Space Network for Global Impairments Comp...

引用

15th International Conference on Communications, COMM 2024

作者： Frunza, Alexandru Choqueuse, vincent Miron, Flavius Azou, Stephane Communications and Information Technology Military Technical Academy Bucharest050141 Romania Lab-STICC CNRS UMR 6285 École Nationale D'Ingénieurs de Brest France

ISBN: (纸本)9798350355956

This paper presents a novel compensation approach based on a parametric State-Space Network that aims to compensate for multiple linear imperfections in coherent optical communications. A communication impaired by residual in-phase/quadrature imbalance, chromatic dispersion, and laser phase noise is considered. The State-Space Network is composed of multiple parametric layers that mitigate the imperfections impact in a global manner. The proposed technique benefits from the augmentation of some conventional compensation algorithms by transforming some fixed parameters into learnable ones. For example, the phase noise compensation layer consists of an modified Kalman filter that has the ability to automatically update its process and observations noises, leading to a better resilience to improper initial tuning. The proposed method outperforms a conventional digital signal processing compensation scheme in certain scenarios, making it promising for future extensions. © 2024 IEEE.

关键词： Chromatic dispersion

来源：评论

学校读者我要写书评

暂无评论

Study of motion delay correction algorithms in time synchronization

Study of motion delay correction algorithms in time synchron...

引用

2024 International Conference on Mechatronic Engineering and Artificial Intelligence, MEAI 2024

作者： Liu, Xiaoyi Li, Jiayin Hu, Xiaoyang Ladimirovich, Perliuk Vladimir Shao, Yunzhuo College of Equipment Engineering Shenyang Ligong University Liaoning Province Shenyang110159 China Institute of Aerospace Instruments and Systems St. Petersburg University of Aerospace Instrumentation St. Petersburg190000 Russia Inner Mongolia First Machinery Group Co Ltd. Inner Mongolia Autonomous Region Baotou014030 China

ISBN: (纸本)9781510689176

As human exploration and research of science extends from the ground to deep space, for satellites with faster relative motion speeds and time information that is difficult to accurately obtain the time, this paper proposes a POLA motion delay correction algorithm, which only needs the motion speed of one of the two parties of time synchronization and the position information of both parties to correct the motion delay difference, so that the two-way time synchronization accuracy is not affected by the speed accuracy of the poorer party The algorithm only needs the velocity and position information of one of the time synchronization parties to correct the delay difference, so that the two-way time synchronization accuracy is not affected by the velocity error of the party with poor velocity accuracy. The effectiveness of the algorithm is verified through simulation tests. © 2025 SPIE.

关键词： Clocks Satellites Motion measurement Ranging Antennas Motion analysis Signal processing Aerospace engineering Kinematics Receivers

来源：评论

学校读者我要写书评

暂无评论

Design of polarimetric camera based on the single-layer twisted nematic liquid crystal device 12

Design of polarimetric camera based on the single-layer twis...

引用

SPIE 12th International Symposium on Multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Ye, Mao Zhu, Wenjie Liu, Kewei Zhang, Xinyu Institude of Artificial Intelligence Huazhong University of Science and Technology Hubei Wuhan430074 China National Key Laboratory of Science & Technology on Multispectral Information Processing Huazhong University of Science & Technology Wuhan430074 China School of Artificial Intelligence & Automation Huazhong University of Science & Technology Wuhan430074 China

ISBN: (数字)9781510674929

ISBN: (纸本)9781510674912

Polarization is the asymmetry of a light wave's electric field vibration direction with respect to its propagation direction, as a crucial clue for describing the light, which is one of the most apparent signs that distinguishes transverse waves from longitudinal waves. The current mainstream polarimetric cameras typically adopt a division of focal plane imaging architecture, in which a metal wire-grid structure is coupled with a detector to acquire the polarization state of the target. However, the structure of the division of focal plane reduces effective spatial resolution of the detector and requires complex registration algorithms to achieve pixel-level polarization acquisition, which leads to high equipment costs and impedes the development and application of polarimetric cameras in industrial production. In this paper, a single-layer twisted nematic liquid crystal (TNLC) is inserted to the imaging optical path of traditional camera to realize the polarization acquisition, allowing for a cost-effective transition from traditional devices to polarization imaging systems. The imaging detector coupled with the TNLC device can acquire polarization states ranging from 10 to 90-degree by adjusting the external voltage applied on the LC device. Moreover, a polarization angle calibration method based on a single-layer TNLC is proposed in this paper, providing a reliable reference for electrically controlled polarization angle acquisition. The experimental results acquired by presented imaging system demonstrate the feasibility and effectiveness of the proposed method. The TNLC based imaging scheme presented in this paper provides a solid foundation for developing simple, low-cost, and efficient polarimetric cameras. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Efficient Low Light video Enhancement Based on Improved Retinex algorithms

Efficient Low Light Video Enhancement Based on Improved Reti...

引用

2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Lee, Sung-Ling Yang, Shih-Hsuan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350313154

videos shot in low-light environments suffer from low contrast and high noise. In this paper, an improved zero-reference low-light enhancement technique for videos based on the Retinex model is presented. The proposed method improves the existing Retinex approaches in several aspects. First, the image features extracted by the VGG network are employed as a part of the input to the generator of the Retinex parameters for increasing temporal stability. Second, a deformable convolution kernel is used to enhance the spatial correlation. Third, the optical flow between frames is approximated as a combination of affine linear transformations for reducing complexity. Compared with the state-of-the-art low-light enhancement algorithms, the proposed method achieves more favorable and stable image qualities in PSNR and SSIM with short processing time. © 2023 IEEE.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Interpreting and understanding the image using deep learning and imprecise information from the monitoring system

Interpreting and understanding the image using deep learning...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Kubanek, Mariusz Bobulski, Janusz Karbowiak, Lukasz Czestochowa University of Technology Department of Computer Science Czestochowa Poland

ISBN: (纸本)9798350324457

The interpretation and understanding of images using deep learning algorithms in monitoring systems is an important area of research in computer vision. In this paper, we propose a novel approach for interpreting and understanding images of human behaviour captured from cameras and drones in monitoring systems. In the work, we presented a pedestrian detection method. This is the first element of a larger system of interpreting the behaviour of traffic participants. We begin by pre-processing the images to remove noise and unwanted artefacts. We then use labelled and unlabelled data to train a deep learning algorithm to accurately classify and predict human behaviour. To account for imprecise information, we incorporate probabilistic models into the algorithm to allow it to make predictions with uncertainty. To evaluate the performance of our proposed approach, we use standard metrics, such as precision, recall, and F1 score, and compare our results to existing methods. We also identify the limitations of existing approaches and propose new methods for interpreting and understanding images that can improve their accuracy and reliability. Our proposed approach has the potential to provide a more accurate and robust method for interpreting and understanding images of human behaviour in monitoring systems. It can be used in various applications like traffic monitoring, security systems, and surveillance. Our results demonstrate the importance of incorporating imprecise information into deep learning algorithms to improve their performance and highlight the potential for future research in this area. © 2023 IEEE.

关键词： autonomous car computer vision pedestrian safety smart city

来源：评论

学校读者我要写书评

暂无评论

A New Traffic Prediction Algorithm with Machine Learning for optical Fiber Communication System 3

A New Traffic Prediction Algorithm with Machine Learning for...

引用

3rd IEEE Asian Conference on Innovation in Technology, ASIANCON 2023

作者： Malhotra, Abhiraj Chitkara University Institute of Engineering and Technology Chitkara University Centre for Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350302288

optical Fiber Communication systems are increasingly used for transport networks due to the low cost, large capacity, and high bit rate of optical transmission [1]. However, effective traffic management and predicting future congestion levels is a critical challenge in order to ensure smooth and reliable operations. Machine learning algorithms can be used to accurately predict the future traffic volumes in such networks, providing real-time information on expected capacity usage and allowing operators to take proactive measures to prevent congestion. In this paper, we propose a novel Machine Learning based traffic prediction algorithm for optical Fiber Communications systems (OFCSs). The proposed algorithm uses a combination of Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) architectures for predicting future traffic patterns. We train the model using a sequence of historical traffic data from an OFCS and evaluate it against benchmarks in terms of prediction accuracy and processing time. The results show that the proposed algorithm can make accurate traffic predictions, with a mean absolute error (MAE) of 0.036 for one-step-ahead predictions and 0.077 for five-steps-ahead. Furthermore, the processing time is significantly less than other benchmark models, providing a practical and reliable approach for predicting future traffic in OFCSs. We also discuss the implications of this study in terms of improving optical fiber capacity utilization and meeting the increased demand of growing data traffic. © 2023 IEEE.

关键词： optical fibers

来源：评论

学校读者我要写书评

暂无评论

MULTISOURCE AND MULTITEMPORAL LAND COVER MAPPING OF GREATER LUZON ISLAND USING GOOGLE EARTH ENGINE

MULTISOURCE AND MULTITEMPORAL LAND COVER MAPPING OF GREATER ...

引用

2023 Philippine Geomatics Symposium, PhilGEOS 2023

作者： Candido, C.G. Blanco, A.C. Borlongan, N.J.B. de la Cruz, R.M. Space Information and Infrastructure Bureau Philippine Space Agency Quezon City1109 Philippines Department of Geodetic Engineering University of the Philippines Diliman Quezon City Philippines

A variety of research endeavors and practical applications necessitate the use of land cover maps. These maps are valuable for tasks such as change detection, forest monitoring, urban expansion monitoring, natural resource mapping, catering to diverse user requirements. While satellite sensors offer essential data for comprehending spatial and temporal variations in land cover, relying on a single satellite system can be limiting, especially considering the potential hindrance of cloud cover in the case of optical sensors. To enhance temporal frequency, it becomes essential to utilize multiple satellite systems, albeit requiring harmonization to ensure consistent outcomes. This study presents a large-scale annual land cover mapping which utilizes harmonized Landsat-8 and Sentinel-2 satellite imagery, in conjunction with supplementary data, and a machine learning algorithm. In addition, the use of powerful computational processing platforms such as Google Earth Engine and Google Colaboratory is now a requirement to manage big geospatial data as well as to run different algorithms for processing and analysis. © Author(s) 2024.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：